I am replicating the example from the documentation of the arch library

import datetime as dt
import sys

import arch.data.sp500
import numpy as np
import pandas as pd
from arch import arch_model

data = arch.data.sp500.load()
market = data["Adj Close"]
returns = 100 * market.pct_change().dropna()

am = arch_model(returns, vol="Garch", p=1, o=0, q=1, dist="Normal")
res = am.fit(last_obs="2011-1-1", update_freq=5)
forecasts = res.forecast(horizon=5)
print(forecasts.variance.dropna().head())
                 h.1       h.2       h.3       h.4       h.5
Date
2010-12-31  0.381757  0.390905  0.399988  0.409008  0.417964
2011-01-03  0.451724  0.460381  0.468976  0.477512  0.485987
2011-01-04  0.428416  0.437236  0.445994  0.454691  0.463326
2011-01-05  0.420554  0.429429  0.438242  0.446993  0.455683
2011-01-06  0.402483  0.411486  0.420425  0.429301  0.438115

I don’t understand the output however. It appears to be showing the 5 day forecast from the respective dates, but why does it start at 2010-12-31? I did specify last obs=’2011-1-1′?